New: deep-learnning

aisec (25)in aisec • 7 years ago
[AISec]Show-and-Fool: Crafting Adversarial Examples for Neural Image Captioning 对抗样本攻陷图像标注系统
针对深度学习系统的对抗性样本攻击问题，来自麻省理工学院，加州大学戴维斯分校，IBM Research 和腾讯 AI Lab 的学者在 arXiv 上发表论文提出对于神经网络图像标注系统（neural image captioning system）的对抗样本生成方法。实验结果显示图像标注系统能够很容易地被欺骗。论文地址：
Downvoting a post can decrease pending rewards and make it less visible. Common reasons:
Disagreement on rewards
Fraud or plagiarism
Hate speech or trolling
Miscategorized content or spam

Submit
$0.00
0

[AISec]Show-and-Fool: Crafting Adversarial Examples for Neural Image Captioning 对抗样本攻陷图像标注系统